Skip to main content
Model Fallback keeps your agent answering by automatically retrying on alternate models when the primary model is overloaded or unavailable.

​
Quick Start

1

One-line resilience

from praisonaiagents import Agent
from praisonaiagents.config import LLMConfig

agent = Agent(
    instructions="You are a helpful assistant",
    llm=LLMConfig(
        model="gpt-4o",
        fallback_models=["claude-3-5-sonnet", "gpt-4o-mini"],
    ),
)
agent.start("Summarise today's news")
2

Cross-provider chain

Use LiteLLM-style prefixes when mixing providers:
from praisonaiagents import Agent
from praisonaiagents.config import LLMConfig

agent = Agent(
    llm=LLMConfig(
        model="openai/gpt-4o",
        fallback_models=["anthropic/claude-3-5-sonnet", "openai/gpt-4o-mini"],
    ),
)

​
How It Works

On transient errors (503, timeout, model overloaded), the agent retries the same turn against the next model in fallback_models. Successful calls stay on the primary model.

​
Configuration Options

OptionTypeDefaultDescription
modelstr— (required)Primary model name
fallback_modelsOptional[List[str]]NoneOrdered fallback chain
base_urlOptional[str]NoneCustom endpoint (Ollama, etc.)
api_keyOptional[str]NoneAPI key (falls back to env vars)
authOptional[Dict[str, str]]NoneExtra auth headers
Pass via Agent(llm=LLMConfig(...)) or Agent(model=LLMConfig(...)). See LLM Config for endpoint and auth details.

​
Common Patterns

Cost degradation — primary is capable; fallbacks get cheaper: ["gpt-4o", "gpt-4o-mini"]. Cross-provider resilience — mix OpenAI and Anthropic so one provider outage does not block the agent. Custom gateway — combine base_url with fallbacks when your proxy fronts multiple models.

​
Best Practices

Useful for rate limits, not full provider outages — a cheap model on the same API may still fail if the provider is down.
Fallback runs the same prompt; a much weaker model may return a worse answer, not a missing one.
Longer chains delay user-visible errors without improving success rates much.
LiteLLM-style names (anthropic/..., openai/...) route credentials correctly across providers.

LLM Configuration

Endpoints, API keys, and auth headers.

Models

Choosing models for agents.

Model Router

Dynamic model selection policies.

Rate Limiter

Throttle requests before they fail.